impulse

R1

Open weights
API id deepseek.r1-v1:0
Amazon Bedrock retires it on 30 Mar 2027 (in 132 days). No API serves it after that.
Input / 1M
$1.35
at Amazon Bedrock
Output / 1M
$5.40
at Amazon Bedrock
Context window
128K
tokens
Max output
8K
tokens per reply
Hosts
1
2 listings
Released
-
date not published

Pricing

List prices at Amazon Bedrock, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.35$5.40

What it costs a month

At Amazon Bedrock list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$810
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$842
  • Coding agent1,000 requests a day, 40K in / 2K out$1,944
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$4,536
Use your own numbers

Where to run it

1 host serve R1. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
deepseek.r1-v1:0
$1.35 / $5.40
Retires 30 Mar 2027
Show 1 more listings: regions, snapshots and variants
Amazon Bedrock
us
us.deepseek.r1-v1:0
$1.35 / $5.40
Retires 30 Mar 2027

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: DeepSeek License (MIT code)
Runtimes: SGLang, TGI, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Amazon Bedrock.

Smaller DeepSeek models

No cheaper DeepSeek model keeps its key capabilities.

Other frontier labs

  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    15% less
  • Grok 4.20 Multi Agent
    xAI · on xAI
    $1.25 / $2.50
    Has every key capability
    34% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    37% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    92% less

Open-weight picks

  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    5% less
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
    15% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    27% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    64% less

Benchmarks

Scores published on the model card.

  • Aider Polyglot64.0%

Call it

Using Amazon Bedrock's API.

Python
from litellm import completion

response = completion(
    model="bedrock/deepseek.r1-v1:0",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does R1 cost?

On Amazon Bedrock, R1 costs $1.35 per million input tokens and $5.40 per million output tokens.

Which APIs offer R1?

R1 runs on 1 API: Amazon Bedrock.

What is R1's context window?

128K tokens, with up to 8K tokens in one reply.

Is R1 being retired?

Amazon Bedrock retires it on 30 Mar 2027. No API serves it after that.

What are cheaper alternatives to R1?

Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (15% less), Grok 4.20 Multi Agent on xAI (34% less) and Qwen4 Max on Alibaba DashScope (5% less). Savings are on a mix of 3 input tokens to 1 output token.

What is R1's API model id?

Use deepseek.r1-v1:0 with Amazon Bedrock.

Sources

Raw catalog entry for deepseek.r1-v1:0 on Amazon Bedrock
{
  "deprecation_date": "2027-03-30",
  "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html",
  "input_cost_per_token": 0.00000135,
  "litellm_provider": "bedrock_converse",
  "max_input_tokens": 128000,
  "max_output_tokens": 8192,
  "mode": "chat",
  "output_cost_per_token": 0.0000054,
  "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html",
  "supports_function_calling": false,
  "supports_reasoning": true,
  "supports_tool_choice": false
}